Triple

T16954342
Position Surface form Disambiguated ID Type / Status
Subject Antvorskov Castle E411257 entity
Predicate locatedIn P40 FINISHED
Object Zealand E38167 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Zealand | Statement: [Antvorskov Castle, locatedIn, Zealand]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zealand
Context triple: [Antvorskov Castle, locatedIn, Zealand]
  • A. Zealand chosen
    Zealand is the largest and most populous island of Denmark, home to the capital city Copenhagen and a central hub of the country’s cultural and economic life.
  • B. Vestland
    Vestland is a county in western Norway known for its dramatic fjords, coastal landscapes, and the city of Bergen.
  • C. Austerlands
    Austerlands is a village in Greater Manchester, England, situated near Lees on the western edge of the Pennines.
  • D. island of Zealand
    The island of Zealand is Denmark’s largest and most populous island, home to the capital city Copenhagen and a central hub of the country’s cultural, economic, and political life.
  • E. Skåneland
    Skåneland is a historical region in southern Scandinavia encompassing the provinces around present-day Skåne, known for its shifting rule between Denmark and Sweden and its central role in medieval Nordic history.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d886c9c9d481909afe222093641cae completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d01b04e88190a72735541b3bb117 completed April 18, 2026, 6:40 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00d464762c8190a734ffdd83633f70 completed May 10, 2026, 6:54 p.m.
Created at: April 10, 2026, 5:31 a.m.